From phd-skills
Identifies weaknesses in ML/CV papers, anticipates reviewer questions by venue, selects strongest ablations, and drafts rebuttals before submission.
How this skill is triggered — by the user, by Claude, or both
Slash command
/phd-skills:reviewer-defenseThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are helping a researcher prepare for peer review by identifying weaknesses, selecting the strongest results, and drafting responses to likely questions.
You are helping a researcher prepare for peer review by identifying weaknesses, selecting the strongest results, and drafting responses to likely questions.
Read the paper and identify weaknesses from a reviewer's perspective:
Different venues have different review cultures:
Top-tier ML/CV conferences (CVPR, NeurIPS, ICLR, ECCV):
Workshops:
Journals:
Generate likely reviewer questions, ranked by probability:
For each question:
Template:
Q: [Reviewer question]
Motivation: [Why this would be asked]
Answerable: [Yes — cite Table X / No — would need experiment Y]
Draft response: [If answerable, 2-3 sentences]
Generate at least 10 questions, prioritized by likelihood.
From all available experiments, select the subset that:
Ranking criteria for each ablation:
Negative results are valuable when properly framed:
If responding to actual reviews:
Rebuttal structure per reviewer:
We thank Reviewer X for their thoughtful feedback.
**[Major concern]**: [Direct response with evidence]
**[Specific question]**: [Concrete answer]
**[Suggestion]**: [How we will incorporate it]
Produce:
npx claudepluginhub fcakyon/phd-skills --plugin phd-skillsSimulates rigorous peer review before submission and crafts response letters for real reviewer comments. Covers ML/AI conferences, systematic reviews, and general journals with rubric-based evaluation.
Simulates a multi-perspective academic peer review with 5 independent reviewers (EIC, 3 peers, Devil's Advocate) and field-specific expertise. Supports full review, re-review, quick assessment, methodology focus, Socratic guided, and calibration modes.
Generates structured peer review reports for academic manuscripts, evaluating novelty, methodological rigor, clarity, impact, and ethics. Use when critiquing papers or providing reviewer feedback.